A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 09:45 UTC
[Bugfix] Fix chat utils tests (#18139)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 14, 2025 at 20:38 UTC
d066e52013be278c7a3bc54ec9799d8457895f4d
1 file changed
+3
-3
tests/entrypoints/test_chat_utils.py
+3
-3
@@ -845,10 +845,10 @@ def test_resolve_hf_chat_template(sample_json_schema, model, use_tools):
845
846
# Test detecting the tokenizer's chat_template
847
chat_template = resolve_hf_chat_template(
848
- model_config,
848
tokenizer,
849
chat_template=None,
850
tools=tools,
851
+ model_config=model_config,
852
)
853
assert isinstance(chat_template, str)
854
@@ -890,10 +890,10 @@ def test_resolve_content_format_hf_defined(model, expected_format):
890
891
# Test detecting the tokenizer's chat_template
892
chat_template = resolve_hf_chat_template(
893
- model_config,
893
tokenizer,
894
chat_template=None,
895
tools=None,
896
+ model_config=model_config,
897
)
898
assert isinstance(chat_template, str)
899
@@ -949,10 +949,10 @@ def test_resolve_content_format_fallbacks(model, expected_format):
949
950
# Test detecting the tokenizer's chat_template
951
chat_template = resolve_hf_chat_template(
952
- model_config,
952
tokenizer,
953
chat_template=None,
954
tools=None,
955
+ model_config=model_config,
956
)
957
assert isinstance(chat_template, str)
958